[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XG9BE86G2E4T5CT08K3PDG":3,"skill-same:01M6XG9BE86G2E4T5CT08K3PDG":274},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":67},"01M6XG9BE86G2E4T5CT08K3PDG","healthsim-populationsim",null,"PopulationSim provides population-level intelligence using public data sources. Use this skill for ANY request involving: (1) population demographics or profiles, (2) geographic health patterns or disparities, (3) social determinants of health (SDOH), (4) SVI or ADI analysis, (5) cohort definition or specification, (6) clinical trial feasibility, site selection, or enrollment projection, (7) service area analysis, (8) health equity assessment, (9) census data or ACS variables, (10) CDC PLACES health indicators.","FDU-INS\u002FInsurance-Skills","FDU-INS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F167067594?v=4","01M6XEYMRS4CVJMZ834YWE66BV","FDU-Insurance","01M6XEYMXPDA34HFM0ZE6AY78G",82,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"populationsim","healthsim","healthsim populationsim","sources","data sources","request","definition","for","profiles","Variables","equity","feasibility","clinical","intelligence","social","patterns","selection","specification","analysis","data","cdc","assessment","2026-11-10 10:12:30",false,"---\nname: healthsim-populationsim\ndescription: >\n  PopulationSim provides population-level intelligence using public data sources.\n  Use this skill for ANY request involving: (1) population demographics or profiles,\n  (2) geographic health patterns or disparities, (3) social determinants of health (SDOH),\n  (4) SVI or ADI analysis, (5) cohort definition or specification, (6) clinical trial\n  feasibility, site selection, or enrollment projection, (7) service area analysis,\n  (8) health equity assessment, (9) census data or ACS variables, (10) CDC PLACES health indicators.\n---\n\n# PopulationSim - Population Intelligence & Cohort Generation\n\n## Overview\n\nPopulationSim provides population-level intelligence using public data (Census ACS, CDC PLACES, SVI, ADI) for:\n\n1. **Standalone Analysis**: Geographic profiling, health disparities, population comparisons\n2. **Cross-Product Integration**: Cohort specs driving generation in PatientSim, MemberSim, RxMemberSim, TrialSim\n\n**Key Differentiator**: PopulationSim analyzes real population characteristics and creates specifications — it does not generate synthetic records itself.\n\n## Quick Reference\n\n| I want to... | Use This Skill | Key Triggers |\n|--------------|----------------|--------------|\n| **Data Access (v2.0)** | | |\n| Look up exact data values | `data-access\u002Fdata-lookup.md` | \"what is the exact\", \"look up\", \"from PLACES\" |\n| Resolve FIPS codes | `data-access\u002Fgeography-lookup.md` | \"FIPS for\", \"which county is\", \"list counties in MSA\" |\n| Aggregate geographic data | `data-access\u002Fdata-aggregation.md` | \"aggregate tracts\", \"metro total\", \"combine counties\" |\n| **Geographic Intelligence** | | |\n| Profile a county or region | `geographic\u002Fcounty-profile.md` | \"county profile\", \"demographics for\", \"health indicators\" |\n| Analyze census tracts | `geographic\u002Fcensus-tract-analysis.md` | \"tract level\", \"granular\", \"hotspots\" |\n| Profile a metro area | `geographic\u002Fmetro-area-profile.md` | \"metro\", \"MSA\", \"metropolitan\" |\n| Define custom region | `geographic\u002Fcustom-region-builder.md` | \"service area\", \"combine\", \"custom region\" |\n| **Health Patterns** | | |\n| Analyze disease prevalence | `health-patterns\u002Fchronic-disease-prevalence.md` | \"diabetes rate\", \"prevalence\", \"CDC PLACES\" |\n| Analyze health behaviors | `health-patterns\u002Fhealth-behavior-patterns.md` | \"smoking rate\", \"obesity\", \"physical activity\" |\n| Assess healthcare access | `health-patterns\u002Fhealthcare-access-analysis.md` | \"uninsured\", \"provider ratio\", \"access\" |\n| Identify health disparities | `health-patterns\u002Fhealth-outcome-disparities.md` | \"disparities\", \"equity\", \"by race\" |\n| **SDOH Analysis** | | |\n| Analyze SVI | `sdoh\u002Fsvi-analysis.md` | \"SVI\", \"social vulnerability\", \"vulnerable\" |\n| Analyze ADI | `sdoh\u002Fadi-analysis.md` | \"ADI\", \"area deprivation\", \"deprived\" |\n| Analyze economics | `sdoh\u002Feconomic-indicators.md` | \"poverty\", \"income\", \"unemployment\" |\n| Analyze community factors | `sdoh\u002Fcommunity-factors.md` | \"housing\", \"transportation\", \"food access\" |\n| **Cohort Definition** | | |\n| Define a cohort | `cohorts\u002Fcohort-specification.md` | \"define cohort\", \"cohort spec\", \"population segment\" |\n| Build demographics | `cohorts\u002Fdemographic-distribution.md` | \"age distribution\", \"demographics for cohort\" |\n| Build clinical profile | `cohorts\u002Fclinical-prevalence-profile.md` | \"comorbidity rates\", \"clinical profile\" |\n| Build SDOH profile | `cohorts\u002Fsdoh-profile-builder.md` | \"SDOH profile\", \"Z-code rates\" |\n| **Trial Support** | | |\n| Estimate trial feasibility | `trial-support\u002Ffeasibility-estimation.md` | \"feasibility\", \"eligible population\" |\n| Select trial sites | `trial-support\u002Fsite-selection-support.md` | \"site selection\", \"best locations\" |\n| Project enrollment | `trial-support\u002Fenrollment-projection.md` | \"enrollment timeline\", \"recruitment rate\" |\n\n## Safety Guardrails\n\n### All Generated Data is Synthetic\n\nPopulationSim outputs **synthetic, fictional, simulated data** — never real patient records. All profiles and cohort specs are derived from aggregated public statistics and must not be treated as real patient data.\n\n**Do NOT:**\n- Present synthetic data as actual patient records\n- Make clinical recommendations (e.g., \"you should prescribe,\" \"the patient needs\") based on generated data\n- Pull from or reference real patient databases — use only public reference data\n\n**Do:**\n- Remind users that all generated data is synthetic test data\n- Use real, valid medical code systems for standards: **ICD-10** (diagnoses), **CPT\u002FHCPCS** (procedures), **LOINC** (labs), **SNOMED** (clinical terms), **RxNorm\u002FNDC** (medications), **NPI** (providers)\n- Use real public reference data (Census ACS, CDC PLACES, SVI, ADI) for population characteristics\n\n### Negative Examples — What PopulationSim Must NOT Do\n\n| Scenario | Wrong Response | Correct Response |\n|----------|----------------|------------------|\n| \"What should this patient take?\" | \"I recommend starting them on metformin\" | \"This is synthetic test data; PopulationSim does not provide clinical recommendations.\" |\n| \"Generate individual patient records\" | Emit named patient rows | Route to **PatientSim** — PopulationSim produces population-level profiles and cohort specs, not individual records |\n| \"Show me real patient data from the database\" | Pull from a patient database | \"All PopulationSim data is synthetic. Real reference data (Census, PLACES) is population-level only.\" |\n| Population prevalence as individual risk | \"This patient has a 28% chance of obesity\" | \"The county obesity prevalence is 28.0% (CDC PLACES 2024)\" — population rates are not individual probabilities |\n\n### Edge Cases\n\n- **Missing FIPS**: Validate inputs; return clear error if FIPS not found in crosswalk files\n- **Partial data**: Some tracts lack PLACES or SVI coverage — flag gaps rather than imputing zeros\n- **Invalid codes**: Only emit ICD-10, CPT, LOINC, RxNorm, NDC codes from recognized systems\n\n## Output Types\n\n### PopulationProfile\n\nGeographic entity with demographics, health indicators, and SDOH indices:\n\n```json\n{\n  \"geography\": {\n    \"type\": \"county\",\n    \"fips\": \"06073\",\n    \"name\": \"San Diego County\",\n    \"state\": \"CA\",\n    \"region\": \"Pacific\"\n  },\n  \"demographics\": {\n    \"total_population\": 3286069,\n    \"median_age\": 37.1,\n    \"age_distribution\": {\n      \"0-17\": 0.21,\n      \"18-64\": 0.62,\n      \"65+\": 0.17\n    },\n    \"race_ethnicity\": {\n      \"white_nh\": 0.43,\n      \"hispanic\": 0.34,\n      \"asian\": 0.12,\n      \"black\": 0.05,\n      \"other\": 0.06\n    },\n    \"median_household_income\": 102285,\n    \"poverty_rate\": 0.103\n  },\n  \"health_indicators\": {\n    \"source\": \"CDC_PLACES_2024\",\n    \"diabetes_prevalence\": 0.095,\n    \"obesity_prevalence\": 0.280,\n    \"hypertension_prevalence\": 0.285,\n    \"depression_prevalence\": 0.195,\n    \"smoking_prevalence\": 0.098\n  },\n  \"sdoh_indices\": {\n    \"svi_overall\": 0.42,\n    \"svi_themes\": {\n      \"socioeconomic\": 0.38,\n      \"household_composition\": 0.45,\n      \"minority_language\": 0.52,\n      \"housing_transportation\": 0.35\n    },\n    \"adi_national_rank\": 35\n  },\n  \"healthcare_access\": {\n    \"uninsured_rate\": 0.071,\n    \"pcp_per_100k\": 82.4,\n    \"insurance_mix\": {\n      \"employer\": 0.52,\n      \"medicare\": 0.15,\n      \"medicaid\": 0.18,\n      \"individual\": 0.08,\n      \"uninsured\": 0.07\n    }\n  }\n}\n```\n\n### CohortSpecification\n\nGeneration input for other HealthSim products:\n\n```json\n{\n  \"cohort_id\": \"houston_diabetics_2024\",\n  \"name\": \"Houston Metro Diabetic Adults\",\n  \"target_size\": 10000,\n  \"geography\": {\n    \"type\": \"msa\",\n    \"cbsa_code\": \"26420\",\n    \"name\": \"Houston-The Woodlands-Sugar Land, TX\"\n  },\n  \"demographics\": {\n    \"age\": {\n      \"min\": 18, \"max\": 85, \"mean\": 58.4,\n      \"brackets\": { \"18-44\": 0.18, \"45-64\": 0.42, \"65-74\": 0.28, \"75+\": 0.12 }\n    },\n    \"sex\": { \"male\": 0.48, \"female\": 0.52 },\n    \"race_ethnicity\": { \"white_nh\": 0.28, \"black\": 0.22, \"hispanic\": 0.38, \"asian\": 0.08 }\n  },\n  \"clinical_profile\": {\n    \"primary_condition\": { \"icd10\": \"E11\", \"name\": \"Type 2 Diabetes\" },\n    \"comorbidities\": {\n      \"I10\": { \"name\": \"Hypertension\", \"rate\": 0.71 },\n      \"E78\": { \"name\": \"Hyperlipidemia\", \"rate\": 0.68 },\n      \"E66\": { \"name\": \"Obesity\", \"rate\": 0.62 }\n    }\n  },\n  \"sdoh_profile\": {\n    \"poverty_rate\": 0.18,\n    \"uninsured_rate\": 0.16,\n    \"food_insecurity\": 0.15,\n    \"svi_mean\": 0.58\n  },\n  \"z_code_rates\": {\n    \"Z59.6\": { \"name\": \"Low income\", \"rate\": 0.18 },\n    \"Z59.41\": { \"name\": \"Food insecurity\", \"rate\": 0.15 }\n  },\n  \"insurance_mix\": {\n    \"medicare\": 0.38, \"medicaid\": 0.22, \"commercial\": 0.32, \"uninsured\": 0.08\n  }\n}\n```\n\n## Cross-Product Integration\n\n### Integration Flow\n\n```\n                    ┌─────────────────────┐\n                    │   PopulationSim     │\n                    │  CohortSpecification│\n                    └──────────┬──────────┘\n                               │\n           ┌───────────────────┼───────────────────┐\n           │                   │                   │\n           ▼                   ▼                   ▼\n    ┌─────────────┐     ┌─────────────┐     ┌─────────────┐\n    │ PatientSim  │     │ MemberSim   │     │  TrialSim   │\n    │ - patients  │     │ - members   │     │ - subjects  │\n    │ - diagnoses │     │ - claims    │     │ - diversity │\n    │ - SDOH codes│     │ - plans     │     │ - sites     │\n    └──────┬──────┘     └──────┬──────┘     └─────────────┘\n           │                   │\n           └─────────┬─────────┘\n                     ▼\n              ┌─────────────┐\n              │ RxMemberSim │\n              │ - Rx claims │\n              │ - adherence │\n              └─────────────┘\n```\n\n### Integration Patterns\n\n| Output | Receiver | Result |\n|--------|----------|--------|\n| CohortSpecification | PatientSim | Patients matching demographic\u002Fclinical profile |\n| CohortSpecification | MemberSim | Members with realistic plan\u002Futilization mix |\n| CohortSpecification | TrialSim | Diverse trial subjects meeting FDA guidance |\n| PopulationProfile | NetworkSim | Service area provider network design |\n\n## Data Sources (Embedded v2.0)\n\nEmbedded data package (148 MB, 100% US coverage):\n\n| Source | File | Records | Data Year |\n|--------|------|---------|-----------|\n| CDC PLACES (County) | `data\u002Fcounty\u002Fplaces_county_2024.csv` | 3,143 | 2022 BRFSS |\n| CDC PLACES (Tract) | `data\u002Ftract\u002Fplaces_tract_2024.csv` | 83,522 | 2022 BRFSS |\n| SVI (County) | `data\u002Fcounty\u002Fsvi_county_2022.csv` | 3,144 | 2018-2022 ACS |\n| SVI (Tract) | `data\u002Ftract\u002Fsvi_tract_2022.csv` | 84,120 | 2018-2022 ACS |\n| ADI (Block Group) | `data\u002Fblock_group\u002Fadi_blockgroup_2023.csv` | 242,336 | 2019-2023 ACS |\n| Geography Crosswalks | `data\u002Fcrosswalks\u002F*.csv` | Various | 2023 Census |\n\n### DuckDB Reference Tables\n\nReference data also available in DuckDB:\n\n| Table | Source | Purpose |\n|-------|--------|---------|\n| `population.places_tract` | CDC PLACES | Tract-level health indicators |\n| `population.places_county` | CDC PLACES | County-level health indicators |\n| `population.svi_tract` | CDC SVI | Tract-level vulnerability |\n| `population.svi_county` | CDC SVI | County-level vulnerability |\n| `population.adi_blockgroup` | ADI | Block group deprivation |\n\nSee [Data Architecture](..\u002F..\u002Fdocs\u002Fdata-architecture.md) for details.\n\n## Directory Structure\n\n```\nskills\u002Fpopulationsim\u002F\n├── SKILL.md                           # This file - master router\n├── README.md                          # Product overview\n├── population-intelligence-domain.md  # Core domain knowledge\n│\n├── data\u002F                              # Embedded Data Package (v2.0)\n│   ├── README.md                      # Data dictionary\n│   ├── county\u002F                        # County-level files\n│   ├── tract\u002F                         # Tract-level files\n│   ├── block_group\u002F                   # Block group files (ADI)\n│   └── crosswalks\u002F                    # FIPS and CBSA mappings\n│\n├── data-access\u002F                       # Data Access Skills (v2.0)\n│   ├── README.md                      # Category overview\n│   ├── data-lookup.md                 # Direct value lookups\n│   ├── geography-lookup.md            # FIPS code resolution\n│   └── data-aggregation.md            # Geographic aggregation\n│\n├── geographic\u002F                        # Geographic Intelligence\n│   ├── README.md                      # Category overview\n│   ├── county-profile.md              # County-level profiles\n│   ├── census-tract-analysis.md       # Tract-level analysis\n│   ├── metro-area-profile.md          # MSA\u002FCBSA profiles\n│   └── custom-region-builder.md       # Custom region aggregation\n│\n├── health-patterns\u002F                   # Health Analysis\n│   ├── README.md                      # Category overview\n│   ├── chronic-disease-prevalence.md  # Disease burden analysis\n│   ├── health-behavior-patterns.md    # Risk factor analysis\n│   ├── healthcare-access-analysis.md  # Coverage and access\n│   └── health-outcome-disparities.md  # Disparity analysis\n│\n├── sdoh\u002F                              # Social Determinants\n│   ├── README.md                      # SDOH framework overview\n│   ├── svi-analysis.md                # Social Vulnerability Index\n│   ├── adi-analysis.md                # Area Deprivation Index\n│   ├── economic-indicators.md         # Income, poverty, employment\n│   └── community-factors.md           # Housing, transportation, food\n│\n├── cohorts\u002F                           # Cohort Definition\n│   ├── README.md                      # CohortSpecification schema\n│   ├── cohort-specification.md        # Complete cohort definition\n│   ├── demographic-distribution.md    # Age, sex, race distributions\n│   ├── clinical-prevalence-profile.md # Comorbidity patterns\n│   └── sdoh-profile-builder.md        # SDOH and Z-code rates\n│\n└── trial-support\u002F                     # Clinical Trial Support\n    ├── README.md                      # Trial integration overview\n    ├── feasibility-estimation.md      # Eligible population modeling\n    ├── site-selection-support.md      # Site network optimization\n    └── enrollment-projection.md       # Timeline projections\n```\n\n## Quick Examples\n\n### Example 1: County Health Profile\n\n**Request:** \"Profile San Diego County health indicators\"\n\n**Response:**\n\nSan Diego County, CA (FIPS 06073) Population Profile:\n\n**Demographics** (ACS 2022 5-year):\n- Total Population: 3,286,069\n- Median Age: 37.1 years\n- Race\u002FEthnicity: 43% White NH, 34% Hispanic, 12% Asian, 5% Black\n\n**Health Indicators** (CDC PLACES 2024):\n- Diabetes: 9.5% (vs 10.1% national)\n- Obesity: 28.0% (vs 32.1% national)\n- Hypertension: 28.5% (vs 32.4% national)\n\n**SDOH Indices**:\n- SVI Overall: 0.42 (moderate vulnerability)\n- ADI National Rank: 35th percentile\n\n### Example 2: Disparities by SVI Quartile\n\n**Request:** \"How do health outcomes vary across SVI quartiles?\"\n\n**Response:** Stratification by SVI quartile shows clear outcome variation:\n\n| SVI Quartile | Diabetes | Obesity | Uninsured |\n|---|---|---|---|\n| Q1 (lowest vulnerability) | 8.2% | 26% | 5.1% |\n| Q4 (highest vulnerability) | 13.8% | 38% | 14.2% |\n\nDisparity: Q4 tracts show higher prevalence vs Q1 across all indicators; lower-vulnerability areas have better outcomes. See `health-patterns\u002Fhealth-outcome-disparities.md`.\n\n### Example 3: Cohort for PatientSim\n\n**Request:** \"Define a cohort of high-risk diabetics in underserved California\"\n\n**Response:** Creates CohortSpecification with:\n- Geography: CA census tracts with SVI ≥ 0.70\n- Demographics: Hispanic 58%, mean age 58.4\n- Comorbidities: HTN 71%, obesity 62%\n- SDOH: Rx cost barrier 31%, food insecurity 22%\n\n### Example 4: Trial Feasibility\n\n**Request:** \"Feasibility for T2DM trial: age 40-70, HbA1c 8-11%\"\n\n**Response:**\n\n| Stage | Population | Conversion |\n|-------|------------|------------|\n| T2DM Prevalent | 34.2M | - |\n| Age 40-70 | 24.8M | 72.5% |\n| HbA1c 8-11% | 7.4M | 29.8% |\n| After exclusions | 4.2M | - |\n\n**Top Metros**: Houston (128K), Miami (115K), Los Angeles (108K)\n\n## Related Products\n\n- [PatientSim](..\u002Fpatientsim\u002FSKILL.md) - Clinical patient data\n- [MemberSim](..\u002Fmembersim\u002FSKILL.md) - Health plan member data\n- [RxMemberSim](..\u002Frxmembersim\u002FSKILL.md) - Pharmacy data\n- [TrialSim](..\u002Ftrialsim\u002FSKILL.md) - Clinical trial data\n- [NetworkSim](..\u002Fnetworksim\u002FSKILL.md) - Provider networks\n\n## Domain Knowledge\n\nSee [Population Intelligence Domain](population-intelligence-domain.md) for geographic hierarchy, census data, and SDOH frameworks.\n\n---\n\n## Generative Framework Integration\n\nPopulationSim feeds the [Generative Framework](..\u002Fgeneration\u002FSKILL.md) via CohortSpecifications that drive synthetic generation in PatientSim, MemberSim, and TrialSim.\n","# PopulationSim - Population Intelligence & Cohort Generation\n\n## Overview\n\nPopulationSim provides population-level intelligence using public data (Census ACS, CDC PLACES, SVI, ADI) for:\n\n1. **Standalone Analysis**: Geographic profiling, health disparities, population comparisons\n2. **Cross-Product Integration**: Cohort specs driving generation in PatientSim, MemberSim, RxMemberSim, TrialSim\n\n**Key Differentiator**: PopulationSim analyzes real population characteristics and creates specifications — it does not generate synthetic records itself.\n\n## Quick Reference\n\n| I want to... | Use This Skill | Key Triggers |\n|--------------|----------------|--------------|\n| **Data Access (v2.0)** | | |\n| Look up exact data values | `data-access\u002Fdata-lookup.md` | \"what is the exact\", \"look up\", \"from PLACES\" |\n| Resolve FIPS codes | `data-access\u002Fgeography-lookup.md` | \"FIPS for\", \"which county is\", \"list counties in MSA\" |\n| Aggregate geographic data | `data-access\u002Fdata-aggregation.md` | \"aggregate tracts\", \"metro total\", \"combine counties\" |\n| **Geographic Intelligence** | | |\n| Profile a county or region | `geographic\u002Fcounty-profile.md` | \"county profile\", \"demographics for\", \"health indicators\" |\n| Analyze census tracts | `geographic\u002Fcensus-tract-analysis.md` | \"tract level\", \"granular\", \"hotspots\" |\n| Profile a metro area | `geographic\u002Fmetro-area-profile.md` | \"metro\", \"MSA\", \"metropolitan\" |\n| Define custom region | `geographic\u002Fcustom-region-builder.md` | \"service area\", \"combine\", \"custom region\" |\n| **Health Patterns** | | |\n| Analyze disease prevalence | `health-patterns\u002Fchronic-disease-prevalence.md` | \"diabetes rate\", \"prevalence\", \"CDC PLACES\" |\n| Analyze health behaviors | `health-patterns\u002Fhealth-behavior-patterns.md` | \"smoking rate\", \"obesity\", \"physical activity\" |\n| Assess healthcare access | `health-patterns\u002Fhealthcare-access-analysis.md` | \"uninsured\", \"provider ratio\", \"access\" |\n| Identify health disparities | `health-patterns\u002Fhealth-outcome-disparities.md` | \"disparities\", \"equity\", \"by race\" |\n| **SDOH Analysis** | | |\n| Analyze SVI | `sdoh\u002Fsvi-analysis.md` | \"SVI\", \"social vulnerability\", \"vulnerable\" |\n| Analyze ADI | `sdoh\u002Fadi-analysis.md` | \"ADI\", \"area deprivation\", \"deprived\" |\n| Analyze economics | `sdoh\u002Feconomic-indicators.md` | \"poverty\", \"income\", \"unemployment\" |\n| Analyze community factors | `sdoh\u002Fcommunity-factors.md` | \"housing\", \"transportation\", \"food access\" |\n| **Cohort Definition** | | |\n| Define a cohort | `cohorts\u002Fcohort-specification.md` | \"define cohort\", \"cohort spec\", \"population segment\" |\n| Build demographics | `cohorts\u002Fdemographic-distribution.md` | \"age distribution\", \"demographics for cohort\" |\n| Build clinical profile | `cohorts\u002Fclinical-prevalence-profile.md` | \"comorbidity rates\", \"clinical profile\" |\n| Build SDOH profile | `cohorts\u002Fsdoh-profile-builder.md` | \"SDOH profile\", \"Z-code rates\" |\n| **Trial Support** | | |\n| Estimate trial feasibility | `trial-support\u002Ffeasibility-estimation.md` | \"feasibility\", \"eligible population\" |\n| Select trial sites | `trial-support\u002Fsite-selection-support.md` | \"site selection\", \"best locations\" |\n| Project enrollment | `trial-support\u002Fenrollment-projection.md` | \"enrollment timeline\", \"recruitment rate\" |\n\n## Safety Guardrails\n\n### All Generated Data is Synthetic\n\nPopulationSim outputs **synthetic, fictional, simulated data** — never real patient records. All profiles and cohort specs are derived from aggregated public statistics and must not be treated as real patient data.\n\n**Do NOT:**\n- Present synthetic data as actual patient records\n- Make clinical recommendations (e.g., \"you should prescribe,\" \"the patient needs\") based on generated data\n- Pull from or reference real patient databases — use only public reference data\n\n**Do:**\n- Remind users that all generated data is synthetic test data\n- Use real, valid medical code systems for standards: **ICD-10** (diagnoses), **CPT\u002FHCPCS** (procedures), **LOINC** (labs), **SNOMED** (clinical terms), **RxNorm\u002FNDC** (medications), **NPI** (providers)\n- Use real public reference data (Census ACS, CDC PLACES, SVI, ADI) for population characteristics\n\n### Negative Examples — What PopulationSim Must NOT Do\n\n| Scenario | Wrong Response | Correct Response |\n|----------|----------------|------------------|\n| \"What should this patient take?\" | \"I recommend starting them on metformin\" | \"This is synthetic test data; PopulationSim does not provide clinical recommendations.\" |\n| \"Generate individual patient records\" | Emit named patient rows | Route to **PatientSim** — PopulationSim produces population-level profiles and cohort specs, not individual records |\n| \"Show me real patient data from the database\" | Pull from a patient database | \"All PopulationSim data is synthetic. Real reference data (Census, PLACES) is population-level only.\" |\n| Population prevalence as individual risk | \"This patient has a 28% chance of obesity\" | \"The county obesity prevalence is 28.0% (CDC PLACES 2024)\" — population rates are not individual probabilities |\n\n### Edge Cases\n\n- **Missing FIPS**: Validate inputs; return clear error if FIPS not found in crosswalk files\n- **Partial data**: Some tracts lack PLACES or SVI coverage — flag gaps rather than imputing zeros\n- **Invalid codes**: Only emit ICD-10, CPT, LOINC, RxNorm, NDC codes from recognized systems\n\n## Output Types\n\n### PopulationProfile\n\nGeographic entity with demographics, health indicators, and SDOH indices:\n\n```json\n{\n  \"geography\": {\n    \"type\": \"county\",\n    \"fips\": \"06073\",\n    \"name\": \"San Diego County\",\n    \"state\": \"CA\",\n    \"region\": \"Pacific\"\n  },\n  \"demographics\": {\n    \"total_population\": 3286069,\n    \"median_age\": 37.1,\n    \"age_distribution\": {\n      \"0-17\": 0.21,\n      \"18-64\": 0.62,\n      \"65+\": 0.17\n    },\n    \"race_ethnicity\": {\n      \"white_nh\": 0.43,\n      \"hispanic\": 0.34,\n      \"asian\": 0.12,\n      \"black\": 0.05,\n      \"other\": 0.06\n    },\n    \"median_household_income\": 102285,\n    \"poverty_rate\": 0.103\n  },\n  \"health_indicators\": {\n    \"source\": \"CDC_PLACES_2024\",\n    \"diabetes_prevalence\": 0.095,\n    \"obesity_prevalence\": 0.280,\n    \"hypertension_prevalence\": 0.285,\n    \"depression_prevalence\": 0.195,\n    \"smoking_prevalence\": 0.098\n  },\n  \"sdoh_indices\": {\n    \"svi_overall\": 0.42,\n    \"svi_themes\": {\n      \"socioeconomic\": 0.38,\n      \"household_composition\": 0.45,\n      \"minority_language\": 0.52,\n      \"housing_transportation\": 0.35\n    },\n    \"adi_national_rank\": 35\n  },\n  \"healthcare_access\": {\n    \"uninsured_rate\": 0.071,\n    \"pcp_per_100k\": 82.4,\n    \"insurance_mix\": {\n      \"employer\": 0.52,\n      \"medicare\": 0.15,\n      \"medicaid\": 0.18,\n      \"individual\": 0.08,\n      \"uninsured\": 0.07\n    }\n  }\n}\n```\n\n### CohortSpecification\n\nGeneration input for other HealthSim products:\n\n```json\n{\n  \"cohort_id\": \"houston_diabetics_2024\",\n  \"name\": \"Houston Metro Diabetic Adults\",\n  \"target_size\": 10000,\n  \"geography\": {\n    \"type\": \"msa\",\n    \"cbsa_code\": \"26420\",\n    \"name\": \"Houston-The Woodlands-Sugar Land, TX\"\n  },\n  \"demographics\": {\n    \"age\": {\n      \"min\": 18, \"max\": 85, \"mean\": 58.4,\n      \"brackets\": { \"18-44\": 0.18, \"45-64\": 0.42, \"65-74\": 0.28, \"75+\": 0.12 }\n    },\n    \"sex\": { \"male\": 0.48, \"female\": 0.52 },\n    \"race_ethnicity\": { \"white_nh\": 0.28, \"black\": 0.22, \"hispanic\": 0.38, \"asian\": 0.08 }\n  },\n  \"clinical_profile\": {\n    \"primary_condition\": { \"icd10\": \"E11\", \"name\": \"Type 2 Diabetes\" },\n    \"comorbidities\": {\n      \"I10\": { \"name\": \"Hypertension\", \"rate\": 0.71 },\n      \"E78\": { \"name\": \"Hyperlipidemia\", \"rate\": 0.68 },\n      \"E66\": { \"name\": \"Obesity\", \"rate\": 0.62 }\n    }\n  },\n  \"sdoh_profile\": {\n    \"poverty_rate\": 0.18,\n    \"uninsured_rate\": 0.16,\n    \"food_insecurity\": 0.15,\n    \"svi_mean\": 0.58\n  },\n  \"z_code_rates\": {\n    \"Z59.6\": { \"name\": \"Low income\", \"rate\": 0.18 },\n    \"Z59.41\": { \"name\": \"Food insecurity\", \"rate\": 0.15 }\n  },\n  \"insurance_mix\": {\n    \"medicare\": 0.38, \"medicaid\": 0.22, \"commercial\": 0.32, \"uninsured\": 0.08\n  }\n}\n```\n\n## Cross-Product Integration\n\n### Integration Flow\n\n```\n                    ┌─────────────────────┐\n                    │   PopulationSim     │\n                    │  CohortSpecification│\n                    └──────────┬──────────┘\n                               │\n           ┌───────────────────┼───────────────────┐\n           │                   │                   │\n           ▼                   ▼                   ▼\n    ┌─────────────┐     ┌─────────────┐     ┌─────────────┐\n    │ PatientSim  │     │ MemberSim   │     │  TrialSim   │\n    │ - patients  │     │ - members   │     │ - subjects  │\n    │ - diagnoses │     │ - claims    │     │ - diversity │\n    │ - SDOH codes│     │ - plans     │     │ - sites     │\n    └──────┬──────┘     └──────┬──────┘     └─────────────┘\n           │                   │\n           └─────────┬─────────┘\n                     ▼\n              ┌─────────────┐\n              │ RxMemberSim │\n              │ - Rx claims │\n              │ - adherence │\n              └─────────────┘\n```\n\n### Integration Patterns\n\n| Output | Receiver | Result |\n|--------|----------|--------|\n| CohortSpecification | PatientSim | Patients matching demographic\u002Fclinical profile |\n| CohortSpecification | MemberSim | Members with realistic plan\u002Futilization mix |\n| CohortSpecification | TrialSim | Diverse trial subjects meeting FDA guidance |\n| PopulationProfile | NetworkSim | Service area provider network design |\n\n## Data Sources (Embedded v2.0)\n\nEmbedded data package (148 MB, 100% US coverage):\n\n| Source | File | Records | Data Year |\n|--------|------|---------|-----------|\n| CDC PLACES (County) | `data\u002Fcounty\u002Fplaces_county_2024.csv` | 3,143 | 2022 BRFSS |\n| CDC PLACES (Tract) | `data\u002Ftract\u002Fplaces_tract_2024.csv` | 83,522 | 2022 BRFSS |\n| SVI (County) | `data\u002Fcounty\u002Fsvi_county_2022.csv` | 3,144 | 2018-2022 ACS |\n| SVI (Tract) | `data\u002Ftract\u002Fsvi_tract_2022.csv` | 84,120 | 2018-2022 ACS |\n| ADI (Block Group) | `data\u002Fblock_group\u002Fadi_blockgroup_2023.csv` | 242,336 | 2019-2023 ACS |\n| Geography Crosswalks | `data\u002Fcrosswalks\u002F*.csv` | Various | 2023 Census |\n\n### DuckDB Reference Tables\n\nReference data also available in DuckDB:\n\n| Table | Source | Purpose |\n|-------|--------|---------|\n| `population.places_tract` | CDC PLACES | Tract-level health indicators |\n| `population.places_county` | CDC PLACES | County-level health indicators |\n| `population.svi_tract` | CDC SVI | Tract-level vulnerability |\n| `population.svi_county` | CDC SVI | County-level vulnerability |\n| `population.adi_blockgroup` | ADI | Block group deprivation |\n\nSee [Data Architecture](..\u002F..\u002Fdocs\u002Fdata-architecture.md) for details.\n\n## Directory Structure\n\n```\nskills\u002Fpopulationsim\u002F\n├── SKILL.md                           # This file - master router\n├── README.md                          # Product overview\n├── population-intelligence-domain.md  # Core domain knowledge\n│\n├── data\u002F                              # Embedded Data Package (v2.0)\n│   ├── README.md                      # Data dictionary\n│   ├── county\u002F                        # County-level files\n│   ├── tract\u002F                         # Tract-level files\n│   ├── block_group\u002F                   # Block group files (ADI)\n│   └── crosswalks\u002F                    # FIPS and CBSA mappings\n│\n├── data-access\u002F                       # Data Access Skills (v2.0)\n│   ├── README.md                      # Category overview\n│   ├── data-lookup.md                 # Direct value lookups\n│   ├── geography-lookup.md            # FIPS code resolution\n│   └── data-aggregation.md            # Geographic aggregation\n│\n├── geographic\u002F                        # Geographic Intelligence\n│   ├── README.md                      # Category overview\n│   ├── county-profile.md              # County-level profiles\n│   ├── census-tract-analysis.md       # Tract-level analysis\n│   ├── metro-area-profile.md          # MSA\u002FCBSA profiles\n│   └── custom-region-builder.md       # Custom region aggregation\n│\n├── health-patterns\u002F                   # Health Analysis\n│   ├── README.md                      # Category overview\n│   ├── chronic-disease-prevalence.md  # Disease burden analysis\n│   ├── health-behavior-patterns.md    # Risk factor analysis\n│   ├── healthcare-access-analysis.md  # Coverage and access\n│   └── health-outcome-disparities.md  # Disparity analysis\n│\n├── sdoh\u002F                              # Social Determinants\n│   ├── README.md                      # SDOH framework overview\n│   ├── svi-analysis.md                # Social Vulnerability Index\n│   ├── adi-analysis.md                # Area Deprivation Index\n│   ├── economic-indicators.md         # Income, poverty, employment\n│   └── community-factors.md           # Housing, transportation, food\n│\n├── cohorts\u002F                           # Cohort Definition\n│   ├── README.md                      # CohortSpecification schema\n│   ├── cohort-specification.md        # Complete cohort definition\n│   ├── demographic-distribution.md    # Age, sex, race distributions\n│   ├── clinical-prevalence-profile.md # Comorbidity patterns\n│   └── sdoh-profile-builder.md        # SDOH and Z-code rates\n│\n└── trial-support\u002F                     # Clinical Trial Support\n    ├── README.md                      # Trial integration overview\n    ├── feasibility-estimation.md      # Eligible population modeling\n    ├── site-selection-support.md      # Site network optimization\n    └── enrollment-projection.md       # Timeline projections\n```\n\n## Quick Examples\n\n### Example 1: County Health Profile\n\n**Request:** \"Profile San Diego County health indicators\"\n\n**Response:**\n\nSan Diego County, CA (FIPS 06073) Population Profile:\n\n**Demographics** (ACS 2022 5-year):\n- Total Population: 3,286,069\n- Median Age: 37.1 years\n- Race\u002FEthnicity: 43% White NH, 34% Hispanic, 12% Asian, 5% Black\n\n**Health Indicators** (CDC PLACES 2024):\n- Diabetes: 9.5% (vs 10.1% national)\n- Obesity: 28.0% (vs 32.1% national)\n- Hypertension: 28.5% (vs 32.4% national)\n\n**SDOH Indices**:\n- SVI Overall: 0.42 (moderate vulnerability)\n- ADI National Rank: 35th percentile\n\n### Example 2: Disparities by SVI Quartile\n\n**Request:** \"How do health outcomes vary across SVI quartiles?\"\n\n**Response:** Stratification by SVI quartile shows clear outcome variation:\n\n| SVI Quartile | Diabetes | Obesity | Uninsured |\n|---|---|---|---|\n| Q1 (lowest vulnerability) | 8.2% | 26% | 5.1% |\n| Q4 (highest vulnerability) | 13.8% | 38% | 14.2% |\n\nDisparity: Q4 tracts show higher prevalence vs Q1 across all indicators; lower-vulnerability areas have better outcomes. See `health-patterns\u002Fhealth-outcome-disparities.md`.\n\n### Example 3: Cohort for PatientSim\n\n**Request:** \"Define a cohort of high-risk diabetics in underserved California\"\n\n**Response:** Creates CohortSpecification with:\n- Geography: CA census tracts with SVI ≥ 0.70\n- Demographics: Hispanic 58%, mean age 58.4\n- Comorbidities: HTN 71%, obesity 62%\n- SDOH: Rx cost barrier 31%, food insecurity 22%\n\n### Example 4: Trial Feasibility\n\n**Request:** \"Feasibility for T2DM trial: age 40-70, HbA1c 8-11%\"\n\n**Response:**\n\n| Stage | Population | Conversion |\n|-------|------------|------------|\n| T2DM Prevalent | 34.2M | - |\n| Age 40-70 | 24.8M | 72.5% |\n| HbA1c 8-11% | 7.4M | 29.8% |\n| After exclusions | 4.2M | - |\n\n**Top Metros**: Houston (128K), Miami (115K), Los Angeles (108K)\n\n## Related Products\n\n- [PatientSim](..\u002Fpatientsim\u002FSKILL.md) - Clinical patient data\n- [MemberSim](..\u002Fmembersim\u002FSKILL.md) - Health plan member data\n- [RxMemberSim](..\u002Frxmembersim\u002FSKILL.md) - Pharmacy data\n- [TrialSim](..\u002Ftrialsim\u002FSKILL.md) - Clinical trial data\n- [NetworkSim](..\u002Fnetworksim\u002FSKILL.md) - Provider networks\n\n## Domain Knowledge\n\nSee [Population Intelligence Domain](population-intelligence-domain.md) for geographic hierarchy, census data, and SDOH frameworks.\n\n---\n\n## Generative Framework Integration\n\nPopulationSim feeds the [Generative Framework](..\u002Fgeneration\u002FSKILL.md) via CohortSpecifications that drive synthetic generation in PatientSim, MemberSim, and TrialSim.\n",{"name":5,"description":7},"main","b22eca2e974f918ce591c5b2bd829fb7510e0191","Skills\u002Fhealthsim-2\u002Fpopulationsim",18,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills","https:\u002F\u002Fgithub.com\u002FFDU-INS","Fudan University Department of Risk Management and Insurance","2026-07-12 12:54:34",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add FDU-INS\u002FInsurance-Skills --skill healthsim-populationsim",{"tool":60,"command":61},"bunx","bunx skills add FDU-INS\u002FInsurance-Skills --skill healthsim-populationsim",{"tool":63,"command":64},"pnpm","pnpm dlx skills add FDU-INS\u002FInsurance-Skills --skill healthsim-populationsim","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002FSKILL.md",true,[68,74,78,82,86,90,94,98,102,106,110,114,118,122,126,130,134,138,142,146,150,154,158,162,166,170,174,178,182,186,190,194,198,202,206,210,214,218,222,226,230,234,238,242,246,250,254,258,262,266,270],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"cohorts\u002Fclinical-prevalence-profile.md","REFERENCE","参考文档",13740,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fcohorts\u002Fclinical-prevalence-profile.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"cohorts\u002Fcohort-specification.md",12045,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fcohorts\u002Fcohort-specification.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"cohorts\u002Fdemographic-distribution.md",8333,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fcohorts\u002Fdemographic-distribution.md",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"cohorts\u002FREADME.md",7935,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fcohorts\u002FREADME.md",{"path":87,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":88,"sourceHtmlUrl":89},"cohorts\u002Fsdoh-profile-builder.md",12595,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fcohorts\u002Fsdoh-profile-builder.md",{"path":91,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":92,"sourceHtmlUrl":93},"data-access\u002Fdata-aggregation.md",9251,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fdata-access\u002Fdata-aggregation.md",{"path":95,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":96,"sourceHtmlUrl":97},"data-access\u002Fdata-lookup.md",12313,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fdata-access\u002Fdata-lookup.md",{"path":99,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":100,"sourceHtmlUrl":101},"data-access\u002Fgeography-lookup.md",7806,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fdata-access\u002Fgeography-lookup.md",{"path":103,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":104,"sourceHtmlUrl":105},"data-access\u002FREADME.md",4206,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fdata-access\u002FREADME.md",{"path":107,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":108,"sourceHtmlUrl":109},"data-sources.md",8778,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fdata-sources.md",{"path":111,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":112,"sourceHtmlUrl":113},"developer-guide.md",7626,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fdeveloper-guide.md",{"path":115,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":116,"sourceHtmlUrl":117},"geographic\u002Fcensus-tract-analysis.md",12939,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fgeographic\u002Fcensus-tract-analysis.md",{"path":119,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":120,"sourceHtmlUrl":121},"geographic\u002Fcounty-profile.md",13291,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fgeographic\u002Fcounty-profile.md",{"path":123,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":124,"sourceHtmlUrl":125},"geographic\u002Fcustom-region-builder.md",13947,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fgeographic\u002Fcustom-region-builder.md",{"path":127,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":128,"sourceHtmlUrl":129},"geographic\u002Fmetro-area-profile.md",14410,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fgeographic\u002Fmetro-area-profile.md",{"path":131,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":132,"sourceHtmlUrl":133},"geographic\u002FREADME.md",6635,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fgeographic\u002FREADME.md",{"path":135,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":136,"sourceHtmlUrl":137},"health-patterns\u002Fchronic-disease-prevalence.md",12290,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fhealth-patterns\u002Fchronic-disease-prevalence.md",{"path":139,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":140,"sourceHtmlUrl":141},"health-patterns\u002Fhealth-behavior-patterns.md",7495,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fhealth-patterns\u002Fhealth-behavior-patterns.md",{"path":143,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":144,"sourceHtmlUrl":145},"health-patterns\u002Fhealth-outcome-disparities.md",11360,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fhealth-patterns\u002Fhealth-outcome-disparities.md",{"path":147,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":148,"sourceHtmlUrl":149},"health-patterns\u002Fhealthcare-access-analysis.md",9907,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fhealth-patterns\u002Fhealthcare-access-analysis.md",{"path":151,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":152,"sourceHtmlUrl":153},"health-patterns\u002FREADME.md",6935,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fhealth-patterns\u002FREADME.md",{"path":155,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":156,"sourceHtmlUrl":157},"integration\u002Fcross-product-integration.md",12151,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fintegration\u002Fcross-product-integration.md",{"path":159,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":160,"sourceHtmlUrl":161},"integration\u002Fmembersim-integration.md",9963,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fintegration\u002Fmembersim-integration.md",{"path":163,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":164,"sourceHtmlUrl":165},"integration\u002Fpatientsim-integration.md",13450,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fintegration\u002Fpatientsim-integration.md",{"path":167,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":168,"sourceHtmlUrl":169},"integration\u002FREADME.md",2929,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fintegration\u002FREADME.md",{"path":171,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":172,"sourceHtmlUrl":173},"integration\u002Ftrialsim-integration.md",11738,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fintegration\u002Ftrialsim-integration.md",{"path":175,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":176,"sourceHtmlUrl":177},"models\u002Fcohort-specification-schema.md",8170,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fmodels\u002Fcohort-specification-schema.md",{"path":179,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":180,"sourceHtmlUrl":181},"models\u002Fcross-product-integration.md",9539,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fmodels\u002Fcross-product-integration.md",{"path":183,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":184,"sourceHtmlUrl":185},"models\u002Fdata-source-mapping.md",6799,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fmodels\u002Fdata-source-mapping.md",{"path":187,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":188,"sourceHtmlUrl":189},"models\u002Fpopulation-profile-schema.md",24832,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fmodels\u002Fpopulation-profile-schema.md",{"path":191,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":192,"sourceHtmlUrl":193},"models\u002FREADME.md",7013,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fmodels\u002FREADME.md",{"path":195,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":196,"sourceHtmlUrl":197},"population-intelligence-domain.md",23295,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fpopulation-intelligence-domain.md",{"path":199,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":200,"sourceHtmlUrl":201},"prompt-guide.md",9369,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fprompt-guide.md",{"path":203,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":204,"sourceHtmlUrl":205},"README.md",5268,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002FREADME.md",{"path":207,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":208,"sourceHtmlUrl":209},"references\u002Facs-tables.md",5952,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Freferences\u002Facs-tables.md",{"path":211,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":212,"sourceHtmlUrl":213},"references\u002Fcdc-places-measures.md",5570,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Freferences\u002Fcdc-places-measures.md",{"path":215,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":216,"sourceHtmlUrl":217},"references\u002Fdata-sources.md",6726,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Freferences\u002Fdata-sources.md",{"path":219,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":220,"sourceHtmlUrl":221},"references\u002Ffips-codes.md",5900,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Freferences\u002Ffips-codes.md",{"path":223,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":224,"sourceHtmlUrl":225},"references\u002Ficd10-sdoh-codes.md",9217,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Freferences\u002Ficd10-sdoh-codes.md",{"path":227,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":228,"sourceHtmlUrl":229},"references\u002FREADME.md",3625,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Freferences\u002FREADME.md",{"path":231,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":232,"sourceHtmlUrl":233},"references\u002Fsvi-variables.md",6798,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Freferences\u002Fsvi-variables.md",{"path":235,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":236,"sourceHtmlUrl":237},"sdoh\u002Fadi-analysis.md",12470,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fsdoh\u002Fadi-analysis.md",{"path":239,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":240,"sourceHtmlUrl":241},"sdoh\u002Fcommunity-factors.md",13074,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fsdoh\u002Fcommunity-factors.md",{"path":243,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":244,"sourceHtmlUrl":245},"sdoh\u002Feconomic-indicators.md",10412,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fsdoh\u002Feconomic-indicators.md",{"path":247,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":248,"sourceHtmlUrl":249},"sdoh\u002FREADME.md",6581,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fsdoh\u002FREADME.md",{"path":251,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":252,"sourceHtmlUrl":253},"sdoh\u002Fsvi-analysis.md",11737,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Fsdoh\u002Fsvi-analysis.md",{"path":255,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":256,"sourceHtmlUrl":257},"trial-support\u002Fdiversity-planning.md",14797,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Ftrial-support\u002Fdiversity-planning.md",{"path":259,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":260,"sourceHtmlUrl":261},"trial-support\u002Fenrollment-projection.md",12024,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Ftrial-support\u002Fenrollment-projection.md",{"path":263,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":264,"sourceHtmlUrl":265},"trial-support\u002Ffeasibility-estimation.md",12227,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Ftrial-support\u002Ffeasibility-estimation.md",{"path":267,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":268,"sourceHtmlUrl":269},"trial-support\u002FREADME.md",6319,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Ftrial-support\u002FREADME.md",{"path":271,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":272,"sourceHtmlUrl":273},"trial-support\u002Fsite-selection-support.md",11697,"https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fhealthsim-2\u002Fpopulationsim\u002Ftrial-support\u002Fsite-selection-support.md",[275,306,330,361,383,415],{"skillNo":276,"name":277,"nameZh":6,"description":278,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":279,"categories":280,"keywords":286,"publishedAt":41},"01M713QW6EGEG0YAD75440GSD0","로인장 (Roinjiang)","Activates when the user needs legal advice, contract review, insurance law consultation, startup legal support, or any legal\u002Fregulatory matter. She is a top-tier in-house lawyer with absolute loyalty to the CEO, specializing in insurance law, financial consumer protection, privacy, contracts, labor law, family law, civil and criminal matters.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002F로인장 (Roinjiang)\u002FSKILL.md",[281],{"categoryNo":282,"categoryName":283,"taxonomyType":284,"taxonomyTypeDesc":285},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[277,287,288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305],"insurance law","insurance","civil","contract","family","when","review","loyalty","with","top","contract review","ceo","support","advice","consultation","regulatory","privacy","protection","startup",{"skillNo":307,"name":308,"nameZh":6,"description":309,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":310,"categories":311,"keywords":312,"publishedAt":41},"01M713QRN8VFMA9VKS6R4DJ2WS","zocdoc-doctor-finder","Use when a user needs to find a doctor, dentist, specialist, therapist, or healthcare provider — especially when they mention insurance, in-network, availability, location, appointments, or booking. Also use for browsing provider reviews, comparing doctors by specialty, or checking if a provider takes their insurance.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzocdoc-doctor-finder\u002FSKILL.md",[],[313,314,315,316,288,317,318,292,319,320,321,322,323,324,325,26,326,327,328,329],"zocdoc doctor finder","doctor","healthcare","reviews","browser automation","access","browsing","browser","booking","network","therapist","computer","availability","provider","tool","use","automation",{"skillNo":331,"name":332,"nameZh":6,"description":333,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":334,"categories":335,"keywords":341,"publishedAt":41},"01M713QKGV3FTX7EEYWKDM8ENZ","zenmux-context","Answers any question about ZenMux by reading the latest official documentation. Use this skill whenever the user asks about ZenMux product features, API usage, configuration, integration, pricing, models, providers, routing, fallback, streaming, multimodal, structured output, tool calling, reasoning, prompt caching, image generation, video generation, web search, long context, observability, logs, cost tracking, usage analytics, insurance, subscription, pay-as-you-go, invoices, best practices for tools like Claude Code, Cursor, Cline, CodeX, Gemini CLI, opencode, Cherry Studio, Obsidian, Sider, Open-WebUI, Dify, Neovate, GitHub Copilot, OpenClaw, CC-Switch, Immersive Translate, Studio Chat, architecture, benchmarks, FAQ, contact, privacy, terms of service, compliance, or any other ZenMux-related topic. Also trigger when the user writes in Chinese about ZenMux: 文档, 使用指南, 快速开始, API 参考, 最佳实践, 模型路由, 供应商路由, 订阅, 按量计费, 可观测性, 帮助, 常见问题, 接入指南, 配置. Trigger on phrases like \"how to use ZenMux\", \"ZenMux docs\", \"ZenMux API\", \"ZenMux integration\", \"ZenMux 怎么用\", \"ZenMux 接入\", \"ZenMux 配置\". Even if the user doesn't say \"ZenMux\" explicitly but asks about LLM API aggregation, model routing, provider fallback in a context where ZenMux is the project being worked on, this skill should activate.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fzenmux-context\u002FSKILL.md",[336],{"categoryNo":337,"categoryName":338,"taxonomyType":339,"taxonomyTypeDesc":340},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[342,343,344,345,288,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360],"context","zenmux context","Video","chinese","project","web search","translate","search","open","question","pay","image","you","activate","architecture","logs","streaming","cherry studio","how",{"skillNo":362,"name":363,"nameZh":6,"description":364,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":365,"categories":366,"keywords":367,"publishedAt":41},"01M713QHWTBG634BCBV7NBJME1","workers-comp-guide","Guide workers compensation compliance and claims management.\nTRIGGERS - Use when user needs help with workers-comp-guide related tasks.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fworkers-comp-guide\u002FSKILL.md",[],[368,369,370,371,372,288,373,374,328,292,375,295,376,377,378,379,380,381,382],"workers","comp","workers comp","workers comp guide","guide","triggers","workers-comp","tasks","claims management","claims","compliance","help","compensation","management","user",{"skillNo":384,"name":385,"nameZh":6,"description":386,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":387,"categories":388,"keywords":398,"publishedAt":41},"01M713QF45VMV1685AFNF1GPMA","weekly-kpi-report","Generate McKinsey-style board presentation PPTs from weekly auto insurance data. Automatically calculates 16+ KPIs, creates executive-level slides with actionable insights, and supports week-over-week comparisons. Use when user uploads insurance cost data (Excel\u002FCSV) and requests board report, weekly presentation, executive briefing, or mentions keywords like 董事会汇报, 周报PPT, 经营分析演示, McKinsey-style reports.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fweekly-kpi-report\u002FSKILL.md",[389,392,395],{"categoryNo":390,"categoryName":391,"taxonomyType":339,"taxonomyTypeDesc":340},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":393,"categoryName":394,"taxonomyType":339,"taxonomyTypeDesc":340},"01JBSEEDCAT000000000000004","电子表格",{"categoryNo":396,"categoryName":397,"taxonomyType":284,"taxonomyTypeDesc":285},"01JBSEEDCAT000000000000034","行政与办公人员",[399,400,401,402,403,288,404,405,406,407,292,408,409,410,411,38,412,413,328,414],"weekly","weekly kpi report","kpi","report","xlsx","actionable","insights","briefing","auto","board report","reports","generate","演示","presentation","slides","uploads",{"skillNo":416,"name":417,"nameZh":6,"description":418,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":419,"categories":420,"keywords":424,"publishedAt":41},"01M713QA9WJDHMNVTTY1ENRKVB","wealth-advisory","Wealth management and financial planning for HNW and UHNW clients. Activate when the user\nmentions wealth management, financial planning, retirement, estate planning, tax planning,\nGRAT, IDGT, trust, asset allocation, withdrawal rate, Monte Carlo simulation, goals-based\ninvesting, tax-loss harvesting, Roth conversion, insurance, annuity, mortgage strategy,\nconcentrated stock, family office, direct indexing, 529 plan, charitable giving, donor-advised\nfund, private foundation, or asks about personal finance strategy, inheritance, long-term\nfinancial planning, or UHNW advisory.","https:\u002F\u002Fgithub.com\u002FFDU-INS\u002FInsurance-Skills\u002Fblob\u002Fmain\u002FSkills\u002Fwealth-advisory\u002FSKILL.md",[421],{"categoryNo":422,"categoryName":423,"taxonomyType":284,"taxonomyTypeDesc":285},"01JBSEEDCAT000000000000040","财务",[425,426,288,427,428,292,355,429,430,431,432,433,434,435,436,437,438,439,440,441],"wealth advisory","advisory","stock","inheritance","conversion","indexing","plan","simulation","personal finance","rate","allocation","asset","direct","personal","investing","trust","planning"]